Google: Gemma 3 27B

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning,…

google/gemma-3-27b-it

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's latest open source model, successor to [Gemma 2](google/gemma-2-27b-it)

Specifications & capabilities

Input
text, image
Output
text
Context window · tokens
131072
Knowledge cutoff
2024-08-31
Published model ID
gemma3@gemma-3-27b-it
Capabilities
multimodal, promptCaching, structuredOutputs, toolCalling, visionInput
Description source ↗

Evaluations

101–120 / 153

LMArena

1,406.852

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Medicine And Healthcare
dimension
style
metric
Arena rating
rank
182
sample size
2341
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemma 3 27B IT
confidence lower
1394.1706807984433
confidence upper
1419.5326952185355
Original result ↗

LMArena

1,375.3

source id
lmarena
leaderboard name
LMArena Text Industry Legal And Government
dimension
general
metric
Arena rating
rank
183
sample size
2660
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemma 3 27B IT
confidence lower
1363.7186540971668
confidence upper
1386.8808862886106
Original result ↗

LMArena

1,383.05

source id
lmarena
leaderboard name
LMArena Text Industry Life And Physical And Social Science
dimension
general
metric
Arena rating
rank
184
sample size
7858
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemma 3 27B IT
confidence lower
1375.9704362698442
confidence upper
1390.1302924480437
Original result ↗

LMArena

1,386.218

source id
lmarena
leaderboard name
LMArena Text Style Control French
dimension
style
metric
Arena rating
rank
185
sample size
655
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemma 3 27B IT
confidence lower
1362.4312652066922
confidence upper
1410.0037985138622
Original result ↗

LMArena

1,359.499

source id
lmarena
leaderboard name
LMArena Text Industry Business And Management And Financial Operations
dimension
general
metric
Arena rating
rank
186
sample size
6490
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemma 3 27B IT
confidence lower
1351.880972921948
confidence upper
1367.1160811812463
Original result ↗

LMArena

1,348.193

source id
lmarena
leaderboard name
LMArena Text Style Control Creative Writing
dimension
style
metric
Arena rating
rank
186
sample size
6301
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemma 3 27B IT
confidence lower
1340.4511188303757
confidence upper
1355.9356032094245
Original result ↗

LMArena

1,347.309

source id
lmarena
leaderboard name
LMArena Text Industry Writing And Literature And Language
dimension
general
metric
Arena rating
rank
186
sample size
10582
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemma 3 27B IT
confidence lower
1341.1786988336207
confidence upper
1353.4383953424904
Original result ↗

MMBench

49.3%

source id
mmBench
leaderboard name
physical_relation
dimension
vision
metric
physical_relation
rank
190
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_EN_V11_Data
verified
Yes
metric_kind
physical_relation
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
295
benchmark_evaluation
true
source model id
Gemma3-27B
Original result ↗

MMBench

86.5%

source id
mmBench
leaderboard name
attribute_recognition
dimension
vision
metric
attribute_recognition
rank
192
aggregation scope
status
published
direction
higherIsBetter
conditions
suite
MMBench_TEST_EN_V11_Data
verified
Yes
metric_kind
attribute_recognition
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
mmbench-data.json
source_revision
acb08c72ac038d24cf7785254678efe725354fe91091bfa10a667832ad964b24
metric_population
295
benchmark_evaluation
true
source model id
Gemma3-27B
Original result ↗

LMArena

1,377.787

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Business And Management And Financial Operations
dimension
style
metric
Arena rating
rank
193
sample size
6490
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemma 3 27B IT
confidence lower
1370.114852788818
confidence upper
1385.4597220744486
Original result ↗

LMArena

1,384.223

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Legal And Government
dimension
style
metric
Arena rating
rank
195
sample size
2660
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemma 3 27B IT
confidence lower
1372.5539288186378
confidence upper
1395.8926958853672
Original result ↗

LMArena

1,367.236

source id
lmarena
leaderboard name
LMArena Text Style Control Russian
dimension
style
metric
Arena rating
rank
195
sample size
3434
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemma 3 27B IT
confidence lower
1357.4852690687403
confidence upper
1376.9869020538497
Original result ↗

LMArena

1,354.495

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Writing And Literature And Language
dimension
style
metric
Arena rating
rank
195
sample size
10582
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemma 3 27B IT
confidence lower
1348.2992865931085
confidence upper
1360.6916700223778
Original result ↗

LMArena

1,391.65

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Life And Physical And Social Science
dimension
style
metric
Arena rating
rank
196
sample size
7858
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemma 3 27B IT
confidence lower
1384.4917106370572
confidence upper
1398.8086247641866
Original result ↗

LMArena

1,348.906

source id
lmarena
leaderboard name
LMArena Text Spanish
dimension
general
metric
Arena rating
rank
197
sample size
891
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemma 3 27B IT
confidence lower
1328.857874937519
confidence upper
1368.953588212056
Original result ↗

LMArena

1,349.027

source id
lmarena
leaderboard name
LMArena Text Russian
dimension
general
metric
Arena rating
rank
198
sample size
3434
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemma 3 27B IT
confidence lower
1339.3448833815344
confidence upper
1358.7081539968044
Original result ↗

LMArena

1,357.156

source id
lmarena
leaderboard name
LMArena Text Style Control Spanish
dimension
style
metric
Arena rating
rank
201
sample size
891
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemma 3 27B IT
confidence lower
1336.8577847507427
confidence upper
1377.4536715071076
Original result ↗

LMArena

1,376.533

source id
lmarena
leaderboard name
LMArena Text English
dimension
general
metric
Arena rating
rank
202
sample size
23013
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemma 3 27B IT
confidence lower
1371.8713767188115
confidence upper
1381.1942252947636
Original result ↗

LMArena

1,319.808

source id
lmarena
leaderboard name
LMArena Text Industry Entertainment And Sports And Media
dimension
general
metric
Arena rating
rank
203
sample size
7992
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemma 3 27B IT
confidence lower
1312.9738425754272
confidence upper
1326.6417508412499
Original result ↗

LMArena

1,357.784

source id
lmarena
leaderboard name
LMArena Text Overall
dimension
general
metric
Arena rating
rank
204
sample size
46613
evaluated at
2026-11-09T00:00:00.000Z
source model id
Gemma 3 27B IT
confidence lower
1354.1204684655174
confidence upper
1361.448061991186
Original result ↗

Published prices

1–7 / 7

gemma-3-27b-it ↗

$0.09

Inference provider
cheaperInference
Platform
Cheaper Inference
Unit
input_tokens_per_million
Currency
USD
Billing conditions
zdr
false
protocol
chat_completions
service_tier
standard
Billing label
Input tokens (per 1M)

gemma-3-27b-it ↗

$0.33

Inference provider
cheaperInference
Platform
Cheaper Inference
Unit
output_tokens_per_million
Currency
USD
Billing conditions
zdr
false
protocol
chat_completions
service_tier
standard
Billing label
Output tokens (per 1M)

google/gemma-3-27b-it ↗

$0.08

Inference provider
deepInfra
Platform
DeepInfra
Unit
input_tokens_per_million
Currency
USD
Billing conditions

google/gemma-3-27b-it ↗

$0.16

Inference provider
deepInfra
Platform
DeepInfra
Unit
output_tokens_per_million
Currency
USD
Billing conditions

google/gemma-3-27b-it ↗

$0.04

Inference provider
openRouter
Platform
OpenRouter
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions

google/gemma-3-27b-it ↗

$0.08

Inference provider
openRouter
Platform
OpenRouter
Unit
input_tokens_per_million
Currency
USD
Billing conditions

google/gemma-3-27b-it ↗

$0.35

Inference provider
openRouter
Platform
OpenRouter
Unit
output_tokens_per_million
Currency
USD
Billing conditions

Provider specifications & access

1–4 / 4

gemma-3-27b-it ↗

source model id
gemma-3-27b-it
hosting
gateway
platforms
  • Cheaper Inference
context length
40000
max output tokens
16384
architecture
input_modalities
  • text
output_modalities
  • text
capabilities
  • structuredOutputs
  • toolCalling

Gemma 3 27B PT ↗

source model id
google.gemma-3-27b-it
hosting
bedrock-managed
platforms
  • Amazon Bedrock
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities

    gemma-3-27b-it ↗

    source model id
    publishers/google/models/gemma3@gemma-3-27b-it
    hosting
    vertex-self-deployed
    platforms
    • Google Cloud Vertex AI
    architecture
    input_modalities
    • image
    • text
    output_modalities
    • text
    capabilities
    • multimodal
    • visionInput

    google/gemma-3-27b-it ↗

    source model id
    publishers/hf-google/models/gemma-3-27b-it@001
    hosting
    vertex-self-deployed
    platforms
    • Google Cloud Vertex AI
    architecture
    input_modalities
    • image
    • text
    output_modalities
    • text
    capabilities
    • multimodal
    • visionInput

    Safety assessments

    1–1 / 1

    Foundation Model Transparency Index 2025 ↗

    41 / 100

    source id
    stanfordFMTI
    canonical model id
    google/gemma-3-27b-it
    taxonomy
    transparency
    hazard category
    transparency
    hazard name
    Organization transparency
    policy area
    Google
    assessment type
    organization-level disclosure
    metric
    disclosure_score
    result label
    41 / 100
    sample size
    100
    updated at
    2026-11-09T18:08:05.227Z

    Source specification observations

    1–3 / 3

    openRouter ↗

    field
    context_length
    value
    131072
    normalized value
    131072
    scope
    source-model
    source id
    openRouter
    confidence
    1

    openRouter ↗

    field
    knowledge_cutoff
    reported field
    knowledge_cutoff
    value
    2024-08-31
    normalized value
    2024-08-31
    precision
    day
    scope
    source-model
    source id
    openRouter
    confidence
    1

    openRouter ↗

    field
    max_output_tokens
    value
    117964
    normalized value
    117964
    scope
    source-model
    source id
    openRouter
    confidence
    1

    Original sources

    1–20 / 20

    storage.googleapis.com · Model reference ↗

    Hugging Face · google/gemma-3-27b-it ↗

    DeepInfra · Model page ↗

    Google Cloud · Model page ↗

    Google Cloud · Model page ↗

    OpenRouter · Model page ↗

    api.cheaperinference.com · Source snapshot ↗

    Amazon Web Services · Model page ↗

    Amazon Bedrock · Model documentation ↗

    Amazon Web Services · Catalog ↗

    DeepInfra · Catalog ↗

    Epoch AI · Catalog ↗

    GitHub · Catalog ↗

    GitHub · Catalog ↗

    Google Cloud · Catalog ↗

    Hugging Face · Catalog ↗

    Hugging Face · Catalog ↗

    Hugging Face · Catalog ↗

    LMArena · Catalog ↗

    OpenRouter · Catalog ↗

    Source links

    1–14 / 14

    Explore more models

    Models

    Loading
    EVIDENCE / COMPARISON

    Benchmarks

    Explore every benchmark

    Loading

    These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

    Install TensorTrace